bmilde

I have already tested ADAM on this, convergence is much faster. But the change needs to be made in tensorflows seq2seq model. As you said, its simple: I copied seq2seq_model.py...

"Finally, I cannot fathom a case where a user would want to load weights into a similar architecture but would want to exclude specific weights (which name matching may allow)....

Worth pointing out though, that Benjamins implementation with _param_alignment(shapes0, shapes1) should handle the case correctly where you pass in weights partially, as far as I can tell. So should the...

+1 for more flexibility. As a compromise, the additional argument could be: 'by_name' (default), 'by_shape', 'hard' (old implementation), since dnouri favours the by_name approach. Speaking of additional arguments: an argument...

Thank you for your pull request! Sorry this repository has been inactive for a while. Otherwise looking good. We have updated the Kaldi version in PyKaldi recently and made a...

Do you have a BLAS library (Intel MKL, OpenBlas, ...) installed on your system? On Fri, Nov 26, 2021, 3:39 AM wzy ***@***.***> wrote: > running install_lib > running build_ext...

Can you try to do an installation with python 3.8? On Sun, Jun 20, 2021, 4:30 PM Soroush Hashemi Far ***@***.***> wrote: > I faced the same issue. Any solution?...

Working on that and already registered the project with PyPI. But they have to increase the size limit for us, since the whl packages are quite large. We'll hopefully get...

I've added a install_mkl.sh script to the tools directory that should install MKL for you. This would be the fastest option for Intel processors. For AMD, OpenBLAS (https://www.openblas.net/) might be...

Have you sourced path.sh as described in the README? source path.sh Either you have kaldi installed in the current working dir where you run python or you need to change...